AI Companion Aims to Support Cancer Survivors Between Doctor Visits

For hundreds of thousands of people who finish cancer treatment each year, the end of therapy is often not the end of the story. Fatigue that lingers for months, anxiety that surfaces in the quiet days between appointments, practical worries about work, insurance and nutrition—these are the challenges that fill the gap between clinic visits, when patients are largely on their own. Researchers at Sylvester Comprehensive Cancer Center, part of the University of Miami Miller School of Medicine, believe artificial intelligence could help close that gap, and they have now published a detailed blueprint for how to do it responsibly.

In a proof-of-concept study published in the journal Translational Behavioral Medicine, the Sylvester team describes a framework called Precision AI for Survivorship and Supportive Care, or PRECISION-AI. Rather than a single app or chatbot, the framework is a structured approach to developing, evaluating and implementing AI tools in cancer survivorship and supportive care. Its central promise is personalization: tailoring evidence-based support to each survivor’s evolving needs while keeping clinicians firmly in the loop and building in safety guardrails from the start.

“For many survivors, the hardest part isn’t always treatment itself. It’s what happens afterward, when patients are managing fatigue, anxiety, uncertainty and other challenges between clinic visits,” said Frank Penedo, Ph.D., the study’s lead investigator, director of Sylvester’s Survivorship and Supportive Care Institute and the cancer center’s associate director for population sciences. “We’re exploring whether AI can help extend evidence-based support beyond the walls of the cancer center so survivors feel more connected, informed and supported throughout their journey, while not replacing in-person care and having access to their providers as part of their standard of care.”

The framework did not appear out of thin air. It builds on years of survivorship research and clinical infrastructure already running at Sylvester, most notably a program called My Wellness Check. That system, integrated directly into the electronic health record, asks patients to routinely report symptoms, quality-of-life concerns, practical needs and other survivorship challenges before their appointments. What began as a screening and triage program has grown into one of the richest datasets of its kind: since expanding across the cancer center, My Wellness Check has collected longitudinal patient-reported outcomes, supportive care needs and nutritional data from more than 37,000 ambulatory oncology patients.

That trove of real-world patient data is what makes the AI ambitions technically credible rather than speculative. The researchers evaluated records from a subsample of 25,592 ambulatory cancer survivors followed over 36 months, using the longitudinal data to develop machine-learning models that identify patterns associated with symptom burden and unplanned health care utilization. According to the team, applying these advanced analytic and AI-driven techniques improved predictive precision for unfavorable outcomes by more than 25 percent. In practical terms, that means the models are meaningfully better at flagging which patients are likely to deteriorate, land in the emergency department or struggle with unmanaged symptoms—knowledge that can trigger earlier intervention.

The current work takes that foundation a step further with an AI-enabled platform called My Wellness Support. The platform fuses multiple streams of information—patient-reported outcomes, clinical records and behavioral data—to identify risk patterns and unmet needs for each individual survivor. Those insights then drive a personalized package of support: evidence-based educational resources, symptom-management strategies, referrals and resources to address practical needs, and supportive care recommendations matched to the patient’s specific situation. Rather than generic pamphlets or one-size-fits-all advice, the system aims to deliver the right information at the right moment in each survivor’s trajectory.

The patient-facing experience is built around an AI companion with whom survivors can interact between visits, while the study team and clinicians monitor trends, risk scores and alerts through a dedicated dashboard. That two-sided design reflects a deliberate architectural choice: the AI is positioned as an adjunct, not an autonomous decision-maker. Clinicians retain visibility into what the system is surfacing, and escalations flow through human hands. “A patient may be doing well medically but still be struggling with symptoms, stress or questions that arise between appointments,” said Akina Natori, M.D., MSPH, a Sylvester oncologist and assistant professor in the Miller School’s Division of Medical Oncology. “The goal is not to replace those interactions with clinicians but to create another layer of support that helps identify concerns earlier and gives patients access to trusted, evidence-based information when they need it.”

The emphasis on oversight is not incidental. AI systems in health care have repeatedly stumbled when deployed faster than they could be validated, and the Sylvester team is explicit that its platform is designed to operate within established clinical guidelines and safety guardrails while maintaining human oversight. The project remains in early testing, and the researchers stress that the framework’s purpose is precisely to impose scientific discipline on a field where enthusiasm often outpaces evidence. “New technologies often move faster than the systems designed to evaluate them,” said Sara Fleszar-Pavlović, Ph.D., research assistant professor in the Miller School’s Division of Medical Oncology and director of research operations for Sylvester’s Survivorship and Supportive Care Institute. “That’s why our framework emphasizes scientific validation, transparency and continuous evaluation. If AI is going to become part of adjunctive survivorship and supportive care, we have to ensure it is safe, effective and developed with a range of patient populations in mind.”

That last point—developed with a range of patient populations in mind—touches one of the most persistent problems in digital health. Tools trained on narrow datasets can fail the very patients who need them most, and cancer survivorship spans an enormous diversity of ages, cancer types, cultural backgrounds and levels of digital literacy. By grounding its models in a large, longitudinal, real-world patient population rather than a small research cohort, and by building continuous evaluation into the framework itself, the Sylvester team is attempting to head off those failure modes before deployment rather than after. The framework’s staged approach—develop, evaluate, implement—formalizes what is often an afterthought in technology projects: the science that must happen between a promising prototype and a safe clinical tool.

The stakes are considerable. Survivorship care has long been recognized as an underserved phase of the cancer continuum, with patients frequently describing a sense of abandonment once active treatment ends and follow-up visits grow sparse. If platforms like My Wellness Support can reliably detect worsening symptoms earlier, connect patients to trusted information on demand and ease the burden on overextended clinics, they could reshape what supportive care looks like between appointments. By pairing new technology with rigorous science, the Sylvester researchers hope to help cancer survivors receive the support they need in the vulnerable interval between visits—while establishing a model for how AI can be responsibly integrated into survivorship and supportive care across oncology.

Subject of Research: An AI framework for personalized supportive care in cancer survivorship

Article Title: New AI platform could help cancer survivors get personalized support between doctor visits

Article References: New AI platform could help cancer survivors get personalized support between doctor visits. (n.d.). Original publication

Image Credits: AI Generated

DOI: Not provided

Keywords: cancer survivorship, artificial intelligence, supportive care, patient-reported outcomes, machine learning, Sylvester Comprehensive Cancer Center, My Wellness Check, clinical oversight, symptom management, Translational Behavioral Medicine, personalized medicine, digital health